Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324335391> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4324335391 endingPage "103807" @default.
- W4324335391 startingPage "103807" @default.
- W4324335391 abstract "Many methods focus on aligning image regions with the corresponding text fragments, and ignore that images contain fragments that cannot be expressed by texts. To fully express the information of images and prevent the performance degradation caused by fine-grained information deviating from the core meaning of images, we propose Semantic-embedding Guided Graph Network (SGGN) for cross-modal retrieval. It learns the detail representations of each modality, with an integrated semantic information, by guiding local fragments to capture the internal correlation of cross-modal data and effectively convey the information. To further bridge the semantic gap between different modalities, SGGN uses adversarial network to play a game, and uses graph aggregation network to absorb complementary information of neighbor samples. We evaluate our approach on two datasets. Our method (based on R@10) achieves 97.2% on Flickr30k dataset. On MS-COCO dataset, it reaches 99.2% using 1K test set and 92.0% using 5K test set." @default.
- W4324335391 created "2023-03-16" @default.
- W4324335391 creator A5036777291 @default.
- W4324335391 creator A5053275663 @default.
- W4324335391 creator A5062665642 @default.
- W4324335391 creator A5063481044 @default.
- W4324335391 creator A5091372470 @default.
- W4324335391 date "2023-05-01" @default.
- W4324335391 modified "2023-09-26" @default.
- W4324335391 title "Semantic-embedding Guided Graph Network for cross-modal retrieval" @default.
- W4324335391 cites W2044465660 @default.
- W4324335391 cites W2524097181 @default.
- W4324335391 cites W2795832645 @default.
- W4324335391 cites W2896348597 @default.
- W4324335391 cites W2964216321 @default.
- W4324335391 cites W2999606372 @default.
- W4324335391 cites W3017098848 @default.
- W4324335391 cites W3121848148 @default.
- W4324335391 cites W3131251978 @default.
- W4324335391 cites W3159952799 @default.
- W4324335391 cites W4293581688 @default.
- W4324335391 cites W4307957701 @default.
- W4324335391 cites W4313452645 @default.
- W4324335391 doi "https://doi.org/10.1016/j.jvcir.2023.103807" @default.
- W4324335391 hasPublicationYear "2023" @default.
- W4324335391 type Work @default.
- W4324335391 citedByCount "0" @default.
- W4324335391 crossrefType "journal-article" @default.
- W4324335391 hasAuthorship W4324335391A5036777291 @default.
- W4324335391 hasAuthorship W4324335391A5053275663 @default.
- W4324335391 hasAuthorship W4324335391A5062665642 @default.
- W4324335391 hasAuthorship W4324335391A5063481044 @default.
- W4324335391 hasAuthorship W4324335391A5091372470 @default.
- W4324335391 hasConcept C120665830 @default.
- W4324335391 hasConcept C121332964 @default.
- W4324335391 hasConcept C132525143 @default.
- W4324335391 hasConcept C153180895 @default.
- W4324335391 hasConcept C154945302 @default.
- W4324335391 hasConcept C177264268 @default.
- W4324335391 hasConcept C185592680 @default.
- W4324335391 hasConcept C188027245 @default.
- W4324335391 hasConcept C192209626 @default.
- W4324335391 hasConcept C199360897 @default.
- W4324335391 hasConcept C23123220 @default.
- W4324335391 hasConcept C41008148 @default.
- W4324335391 hasConcept C41608201 @default.
- W4324335391 hasConcept C71139939 @default.
- W4324335391 hasConcept C75564084 @default.
- W4324335391 hasConcept C80444323 @default.
- W4324335391 hasConceptScore W4324335391C120665830 @default.
- W4324335391 hasConceptScore W4324335391C121332964 @default.
- W4324335391 hasConceptScore W4324335391C132525143 @default.
- W4324335391 hasConceptScore W4324335391C153180895 @default.
- W4324335391 hasConceptScore W4324335391C154945302 @default.
- W4324335391 hasConceptScore W4324335391C177264268 @default.
- W4324335391 hasConceptScore W4324335391C185592680 @default.
- W4324335391 hasConceptScore W4324335391C188027245 @default.
- W4324335391 hasConceptScore W4324335391C192209626 @default.
- W4324335391 hasConceptScore W4324335391C199360897 @default.
- W4324335391 hasConceptScore W4324335391C23123220 @default.
- W4324335391 hasConceptScore W4324335391C41008148 @default.
- W4324335391 hasConceptScore W4324335391C41608201 @default.
- W4324335391 hasConceptScore W4324335391C71139939 @default.
- W4324335391 hasConceptScore W4324335391C75564084 @default.
- W4324335391 hasConceptScore W4324335391C80444323 @default.
- W4324335391 hasLocation W43243353911 @default.
- W4324335391 hasOpenAccess W4324335391 @default.
- W4324335391 hasPrimaryLocation W43243353911 @default.
- W4324335391 hasRelatedWork W2744136723 @default.
- W4324335391 hasRelatedWork W2923818335 @default.
- W4324335391 hasRelatedWork W3035116611 @default.
- W4324335391 hasRelatedWork W3044354590 @default.
- W4324335391 hasRelatedWork W3094605108 @default.
- W4324335391 hasRelatedWork W3120440802 @default.
- W4324335391 hasRelatedWork W4212923699 @default.
- W4324335391 hasRelatedWork W4287763734 @default.
- W4324335391 hasRelatedWork W4366999699 @default.
- W4324335391 hasRelatedWork W4385482714 @default.
- W4324335391 hasVolume "93" @default.
- W4324335391 isParatext "false" @default.
- W4324335391 isRetracted "false" @default.
- W4324335391 workType "article" @default.